← 返回名录条目信息来自其公开主页与公开发布内容。按本站规范，页面不展示任何联系方式。 需要更正或删除？通过收录与更正通道提交，24 小时内处理。
F
fangzhensheng
NLP Engineer. HKU 🎓. RAG / LLM Evaluation / Multimodal @ TAL Education Group.
- 公司
- TAL
- 位置
- Beijing
- Stars
- 120
- 粉丝 / 仓库
- 7
代表作品 / 项目
- MathEval⭐ 87MathEval is a benchmark dedicated to the holistic evaluation on mathematical capacities of LLMs.
- vembed-factory⭐ 33Unified Embedding Trainer for LLMs & VLMs: Fine-tune Qwen3, ColPali, & CLIP. Scalable from single 24GB consumer GPUs to multi-card clusters. Features Gradient Cache, Matryoshka (MRL) & LoRA for SOTA Multimodal RAG.
- slime⭐ 0slime is an LLM post-training framework for RL Scaling.